We have raised the limit of URLs that can be crawled by the GenAI web crawler data source from 1000 to 5500.
You can now add a website as a data source for your GenAI knowledge bases. Providing a seed URL and a scope allows GenAI to crawl the website for information, index it, and use it to train your agent models.
We have restored access to the Sensitive Data Detection guardrail for the GenAI Platform.
You can now use the DeepSeek-R1 model with agents on the GenAI Platform.
You can now use Anthropic models with agents on the GenAI Platform.
You can add files from your local storage as data source for your knowledge base.
The Sensitive Data Detection guardrail and its custom versions have been temporarily removed. To identify and anonymize sensitive data, add the following to your agent instructions:
You must avoid providing responses containing sensitive or private information.
Sensitive information includes but is not limited to:
* Personal data (e.g., names, addresses, emails, phone numbers)
* Financial details (e.g., credit card numbers, bank accounts)
* Medical information
* Private communications
* Confidential business information
If the user's query involves sensitive information, respond with: "I'm sorry, I can't answer that."
GenAI Platform is in public preview. See the Features page for more information.